AI on Amit Agarwal Linux Blog

ai_ml_hacking

Wed, 08 Jul 2026 00:00:00 +0530

Awesome AI & ML Pentesting: The Curated Resource Every AI Security Researcher Needs

Artificial Intelligence has become one of the fastest-growing attack surfaces in modern cybersecurity. Organizations are deploying Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) systems, autonomous agents, Model Context Protocol (MCP) servers, AI copilots, and machine learning pipelines at an unprecedented pace.

Unfortunately, security knowledge around these technologies is scattered across hundreds of GitHub repositories, research papers, blog posts, OWASP projects, academic publications, and conference talks.

openrouter fusion - capabilities similar to Anthropic Fable

Mon, 15 Jun 2026 00:00:00 +0530

Openrouter Fusion

Openrouter announced openrouter/fusion, a drop-in model alias that they touted can be as good as Anthropic Fable. So, I thought I will give it a try and here are my observations. But before that, here’s how it works (as described by OpenRouter):

Introducing the Fusion API, the smartest compound model in the market.

Fusion achieves Fable-level intelligence on deep research tasks at half the price.

A panel of configurable models analyzes your prompt in parallel when the judge model thinks it’s needed, letting you build your own LLM councils to:

Run a Local LLM API Server with vLLM (OpenAI-Compatible, Fast, and Simple)

Thu, 25 Dec 2025 00:00:00 +0530

Step-by-step: create a uv virtualenv, install vLLM with the right torch backend, and launch vllm serve to get an OpenAI-compatible local API endpoint.